Explainable Deep Learning Methods in Medical Image Classification: A Survey

The progress made on the last decade in the field of artificial intelligence (AI) has supported a dramatic increase in the accuracy of most computer vision applications. Medical image analysis is one of the applications where the progress made assured human-level accuracy on the classification of different types of medical data (e.g., chest X-rays [90], corneal images [166]). However, and in spite of these advances, automated medical imaging is seldom adopted in clinical practice. According to Zachary Lipton [77], the explanation to this apparent paradox is straightforward, doctors will never trust the decision of an algorithm without understanding its decision process. This fact has raised the need for producing strategies capable of explaining the decision process of AI algorithms, leading subsequently to the creation of a novel research topic named as eXplainable Artificial Intelligence (XAI). According to DARPA [46], XAI aims to "produce more explainable models, while maintaining a high level of learning performance (prediction accuracy); and enable human users to understand, appropriately, trust, and effectively manage the emerging generation of artificially intelligent partners". In spite of its general applicability, XAI is particularly important in high-stake decisions, such as clinical workflow, where the consequences of a wrong decision could lead to human deaths. This is also evidenced by European Union's General Data Protection